This paper presents the implementation of a coprocessor that speeds up Roberts gradient edge dete... more This paper presents the implementation of a coprocessor that speeds up Roberts gradient edge detection on monochromatic images with 256 gray levels. The coprocessor is implemented in a reconfigurable computing system based on a board for PC-based platforms using off-the-shelf FPGAs
One of the difficulties of pattern recognition is developing a good evaluation of the classes pre... more One of the difficulties of pattern recognition is developing a good evaluation of the classes presented in a scene. To suitably describe those classes it is necessary to find feature spaces which allow them to be distinguished from each other. We propose an unsupervised segmentation/classification technique associated with textural description and report the results obtained, which are quite encouraging
The fast evolution of digital video has brought many new multimedia applications and, as a conseq... more The fast evolution of digital video has brought many new multimedia applications and, as a consequence, has increased the amount of research into new technologies that aim at improving the effectiveness and efficiency of video acquisition, archiving, cataloging and indexing, as well as increasing the usability of stored videos. Among possible research areas, video summarization is an important topic that potentially enables faster browsing of large video collections and also more efficient content indexing and access. Essentially, this research area consists of automatically generating a short summary of a video, which can either be a static summary or a dynamic summary. In this paper, we present VSUMM, a methodology for the production of static video summaries. The method is based on color feature extraction from video frames and k-means clustering algorithm. As an additional contribution, we also develop a novel approach for the evaluation of video static summaries. In this evaluation methodology, video summaries are manually created by users. Then, several user-created summaries are compared both to our approach and also to a number of different techniques in the literature. Experimental results show -with a confidence level of 98% -that the proposed solution provided static video summaries with superior quality relative to the approaches to which it was compared.
The ability to filter improper content from multimedia sources based on visual content has import... more The ability to filter improper content from multimedia sources based on visual content has important applications, since text-based filters are clearly insufficient against erroneous and/or malicious associations between text and actual content. In this paper, we investigate a method for detection of nudity in videos based on a bag-of-visual-features representation for frames and an associated voting scheme.
This paper proposes a method that aims to reduce a real scene to a set of regions that contain te... more This paper proposes a method that aims to reduce a real scene to a set of regions that contain text fragments and keep small number of false positives. Text is modeled and characterized as a texture pattern, by employing the QMF wavelet decomposition as a texture feature extractor. Processing includes segmentation and spatial selection of regions and then content-based selection of fragments. Unlike many previous works, text fragments in different scales and resolutions laid against complex backgrounds are segmented without supervision. Tested in four image databases, the method is able to reduce visual noise to 4.69% and reaches 96.5% of coherency between the localized fragments and those generated by manual segmentation.
One of the difficulties in pattern recognition is to develop a good evaluation of the classes pre... more One of the difficulties in pattern recognition is to develop a good evaluation of the classes present on a scene. To suitably describe those classes it is necessary to find feature spaces, which allow distinguishing between them. In this work, we propose an unsupervised segmentation/classification technique based on wavelet textural analysis and self-organizing maps clustering.
In most of video shot boundary detection algorithms, proposed in the literature, several paramete... more In most of video shot boundary detection algorithms, proposed in the literature, several parameters and thresholds have to be set in order to achieve good results. In this paper, to get rid of parameters and thresholds, we explore a supervised classification method for video shot segmentation. We transform the temporal segmentation into a class categorization issue. Our approach defines a uniform framework for combining different kinds of features extracted from the video. Our method does not require any pre-processing step to compensate motion or post-processing filtering to eliminate false detected transitions. The experiments, following strictly the TRECVID 2002 competition protocol, provide very good results dealing with a large amount of features thanks to our kernel-based SVM classification method.
The visual rhythm is a simplification of the video content represented by a 2D image. In this wor... more The visual rhythm is a simplification of the video content represented by a 2D image. In this work, the video segmentation problem is transformed into a problem of pattern detection, where each video effect is transformed into a different pattern on the visual rhythm. To detect sharp video transitions (cuts) we use topological and morphological tools instead of using a dissimilarity measure. Thus, we propose a method to detect sharp video transitions between two consecutive shots. We present a comparative analysis of our method with respect to some other methods. We also propose a variant of this method to detect the position of flashes in a video.
The video segmentation problem consists in the identification of the boundary between consecutive... more The video segmentation problem consists in the identification of the boundary between consecutive shots. The common approach to solve this problem is based on dissimilarity measures between frames. In this work, the video segmentation problem is transformed into a problem of pattern detection, where each video event is transformed into a different pattern on a 2D image, called visual rhythm, obtained by a specific transformation. In our analysis we use topological and morphological tools to detect cuts. Also, we use discrete line analysis and max tree analysis to detect fade transitions and flashes, respectively. We present a comparative analysis of our method for cut detection with respect to some other methods, which shows the better results of our method.
The boundary identification represents an interesting and difficult problem in image processing, ... more The boundary identification represents an interesting and difficult problem in image processing, mainly if two flat zones are separated by a gradual transition. The most common operators work very well for sharp edges, but fail for gradual transitions. In this work, we have done a characterization for gradient by a study of the opening residues. This characterization is useful to identify and classify sharp and gradual transitions between two consecutive flat zones according to a size criterion.
The video segmentation problem can be regarded as a problem of detecting the fundamental video un... more The video segmentation problem can be regarded as a problem of detecting the fundamental video units (shots). Due to different ways of linking two consecutive shots this task turns out to be difficult. In this work, we propose a method to detect both cuts and gradual transitions by image segmentation tools instead of using dissimilarity measures or mathematical models. Firstly, the video is transformed into a 2D image, called visual rhythm by sub-sampling. Afterwards, we apply image processing tools to detect all vertical aligned transitions in this image. The main operator applied here is the morphological multiscale gradient. We also present some experimental results.
The video segmentation problem can be regarded as a problem of detecting the fundamental video un... more The video segmentation problem can be regarded as a problem of detecting the fundamental video units (shots). Due to different ways of linking two consecutive shots this task turns out to be difficult. In this work, we propose a method to detect a type of gradual transition, the fade, by image segmentation tools instead of using dissimilarity measures or mathematical models. Firstly, the video is transformed into a 2D image considering the histogram information, called visual rhythm by histogram. Afterwards, we apply image processing tools to detect specified patterns in this image.
Abstract Due to the conditions of storage, old movies may present different defect types of diffe... more Abstract Due to the conditions of storage, old movies may present different defect types of different shapes and sizes. In this work, we propose a method for old movie restoration using opening by surface which eliminates image information by area attribute, independent of the ...
This paper presents the implementation of a coprocessor that speeds up Roberts gradient edge dete... more This paper presents the implementation of a coprocessor that speeds up Roberts gradient edge detection on monochromatic images with 256 gray levels. The coprocessor is implemented in a reconfigurable computing system based on a board for PC-based platforms using off-the-shelf FPGAs
One of the difficulties of pattern recognition is developing a good evaluation of the classes pre... more One of the difficulties of pattern recognition is developing a good evaluation of the classes presented in a scene. To suitably describe those classes it is necessary to find feature spaces which allow them to be distinguished from each other. We propose an unsupervised segmentation/classification technique associated with textural description and report the results obtained, which are quite encouraging
The fast evolution of digital video has brought many new multimedia applications and, as a conseq... more The fast evolution of digital video has brought many new multimedia applications and, as a consequence, has increased the amount of research into new technologies that aim at improving the effectiveness and efficiency of video acquisition, archiving, cataloging and indexing, as well as increasing the usability of stored videos. Among possible research areas, video summarization is an important topic that potentially enables faster browsing of large video collections and also more efficient content indexing and access. Essentially, this research area consists of automatically generating a short summary of a video, which can either be a static summary or a dynamic summary. In this paper, we present VSUMM, a methodology for the production of static video summaries. The method is based on color feature extraction from video frames and k-means clustering algorithm. As an additional contribution, we also develop a novel approach for the evaluation of video static summaries. In this evaluation methodology, video summaries are manually created by users. Then, several user-created summaries are compared both to our approach and also to a number of different techniques in the literature. Experimental results show -with a confidence level of 98% -that the proposed solution provided static video summaries with superior quality relative to the approaches to which it was compared.
The ability to filter improper content from multimedia sources based on visual content has import... more The ability to filter improper content from multimedia sources based on visual content has important applications, since text-based filters are clearly insufficient against erroneous and/or malicious associations between text and actual content. In this paper, we investigate a method for detection of nudity in videos based on a bag-of-visual-features representation for frames and an associated voting scheme.
This paper proposes a method that aims to reduce a real scene to a set of regions that contain te... more This paper proposes a method that aims to reduce a real scene to a set of regions that contain text fragments and keep small number of false positives. Text is modeled and characterized as a texture pattern, by employing the QMF wavelet decomposition as a texture feature extractor. Processing includes segmentation and spatial selection of regions and then content-based selection of fragments. Unlike many previous works, text fragments in different scales and resolutions laid against complex backgrounds are segmented without supervision. Tested in four image databases, the method is able to reduce visual noise to 4.69% and reaches 96.5% of coherency between the localized fragments and those generated by manual segmentation.
One of the difficulties in pattern recognition is to develop a good evaluation of the classes pre... more One of the difficulties in pattern recognition is to develop a good evaluation of the classes present on a scene. To suitably describe those classes it is necessary to find feature spaces, which allow distinguishing between them. In this work, we propose an unsupervised segmentation/classification technique based on wavelet textural analysis and self-organizing maps clustering.
In most of video shot boundary detection algorithms, proposed in the literature, several paramete... more In most of video shot boundary detection algorithms, proposed in the literature, several parameters and thresholds have to be set in order to achieve good results. In this paper, to get rid of parameters and thresholds, we explore a supervised classification method for video shot segmentation. We transform the temporal segmentation into a class categorization issue. Our approach defines a uniform framework for combining different kinds of features extracted from the video. Our method does not require any pre-processing step to compensate motion or post-processing filtering to eliminate false detected transitions. The experiments, following strictly the TRECVID 2002 competition protocol, provide very good results dealing with a large amount of features thanks to our kernel-based SVM classification method.
The visual rhythm is a simplification of the video content represented by a 2D image. In this wor... more The visual rhythm is a simplification of the video content represented by a 2D image. In this work, the video segmentation problem is transformed into a problem of pattern detection, where each video effect is transformed into a different pattern on the visual rhythm. To detect sharp video transitions (cuts) we use topological and morphological tools instead of using a dissimilarity measure. Thus, we propose a method to detect sharp video transitions between two consecutive shots. We present a comparative analysis of our method with respect to some other methods. We also propose a variant of this method to detect the position of flashes in a video.
The video segmentation problem consists in the identification of the boundary between consecutive... more The video segmentation problem consists in the identification of the boundary between consecutive shots. The common approach to solve this problem is based on dissimilarity measures between frames. In this work, the video segmentation problem is transformed into a problem of pattern detection, where each video event is transformed into a different pattern on a 2D image, called visual rhythm, obtained by a specific transformation. In our analysis we use topological and morphological tools to detect cuts. Also, we use discrete line analysis and max tree analysis to detect fade transitions and flashes, respectively. We present a comparative analysis of our method for cut detection with respect to some other methods, which shows the better results of our method.
The boundary identification represents an interesting and difficult problem in image processing, ... more The boundary identification represents an interesting and difficult problem in image processing, mainly if two flat zones are separated by a gradual transition. The most common operators work very well for sharp edges, but fail for gradual transitions. In this work, we have done a characterization for gradient by a study of the opening residues. This characterization is useful to identify and classify sharp and gradual transitions between two consecutive flat zones according to a size criterion.
The video segmentation problem can be regarded as a problem of detecting the fundamental video un... more The video segmentation problem can be regarded as a problem of detecting the fundamental video units (shots). Due to different ways of linking two consecutive shots this task turns out to be difficult. In this work, we propose a method to detect both cuts and gradual transitions by image segmentation tools instead of using dissimilarity measures or mathematical models. Firstly, the video is transformed into a 2D image, called visual rhythm by sub-sampling. Afterwards, we apply image processing tools to detect all vertical aligned transitions in this image. The main operator applied here is the morphological multiscale gradient. We also present some experimental results.
The video segmentation problem can be regarded as a problem of detecting the fundamental video un... more The video segmentation problem can be regarded as a problem of detecting the fundamental video units (shots). Due to different ways of linking two consecutive shots this task turns out to be difficult. In this work, we propose a method to detect a type of gradual transition, the fade, by image segmentation tools instead of using dissimilarity measures or mathematical models. Firstly, the video is transformed into a 2D image considering the histogram information, called visual rhythm by histogram. Afterwards, we apply image processing tools to detect specified patterns in this image.
Abstract Due to the conditions of storage, old movies may present different defect types of diffe... more Abstract Due to the conditions of storage, old movies may present different defect types of different shapes and sizes. In this work, we propose a method for old movie restoration using opening by surface which eliminates image information by area attribute, independent of the ...
Uploads
Papers by Arnaldo Araújo